Deep Reinforcement Learning for Simulation-Based Determination of COVID-19 Pandemic Mitigation Policies

Authors : Mahmut Lütfullah ÖZBİLEN, Emre EĞRİBOZ, Ruşen HALEPMOLLASI, İsmail BİLGEN, Mehmet HAKLIDIR

Pages : 29-38

View : 53 | Download : 13

Publication Date : 2021-09-30

Article Type : Other Papers

Abstract :A global health emergency has been declared by WHO at the beginning of 2020 based on the increasing number of cases in the COVID-19 epidemic. Governments around the world have taken unprecedented measures. However, there is no guarantee that the measures taken are best to mitigate the effect of pandemic. We investigate the impact of government policies regarding interventions on deaths related to the COVID-19 and mitigation of the economic decline. In a simulation environment, we use Reinforcement Learning insert ignore into journalissuearticles values(RL); to explore the optimal policies to prevent COVID-19 outbreak. We use a specific simulator called PandemicSimulator which has detailed abilities to simulate spread of disease and people interactions at different locations. The simulator is utilized to train RL agents to take mitigation policies with minimum economic damage of the pandemic without exceeding the hospital capacity. We use Deep Q Networks to train the RL agent. We compare the performance of the our agent’s policy with the policy applied by the United Kingdom in terms of critical patients, deaths and economic damage. Results show that policies improved by the RL agent can help decision makers in the pandemic mitigation policies.
Keywords : reinforcement learning, deep learning, COVID 19, pandemic

ORIGINAL ARTICLE URL